The effect of small tumor volumes on studies of intratumoral heterogeneity of tracer uptake

Robustness of textural analysis features in quantitative 99 mTc and 177Lu SPECT-CT phantom acquisitions

BACKGROUND

Textural Analysis features in molecular imaging require to be robust under repeat measurement and to be independent of volume for optimum use in clinical studies. Recent EANM and SNMMI guidelines for radiomics provide advice on the potential use of phantoms to identify robust features (Hatt in EJNMMI, 2022). This study applies the suggested phantoms to use in SPECT quantification for two radionuclides, 99 mTc and 177Lu.

METHODS

Acquisitions were made with a uniform phantom to test volume dependency and with a customised 'Revolver' phantom, based on the PET phantom described in Hatt (EJNMMI, 2022) but with local adaptations for SPECT. Each phantom was filled separately with 99 mTc and 177Lu. Sixty-seven Textural Analysis features were extracted and tested for robustness and volume dependency.

RESULTS

Features showing high volume dependency or high Coefficient of Variation (indicating poor repeatability) were removed from the list of features that may be suitable for use in clinical studies. After feature reduction, there were 39 features for 99 mTc and 33 features for 177Lu remaining.

CONCLUSION

The use of a uniform phantom to test volume dependency and a Revolver phantom to identify repeatable Textural Analysis features is possible for quantitative SPECT using 99 mTc or 177Lu. Selection of such features is likely to be centre-dependent due to differences in camera performance as well as acquisition and reconstruction protocols.

A Tumor Volume Segmentation Algorithm Based on Radiomics Features in FDG-PET in Lung Cancer Patients, Validated Using Surgical Specimens

BACKGROUND

Although the integration of positron emission tomography into radiation therapy treatment planning has become part of clinical routine, the best method for tumor delineation is still a matter of debate. In this study, therefore, we analyzed a novel, radiomics-feature-based algorithm in combination with histopathological workup for patients with non-small-cell lung cancer.

METHODS

A total of 20 patients with biopsy-proven lung cancer who underwent [18F]fluorodeoxyglucose positron emission/computed tomography (FDG-PET/CT) examination before tumor resection were included. Tumors were segmented in positron emission tomography (PET) data using previously reported algorithms based on three different radiomics features, as well as a threshold-based algorithm. To obtain gold-standard results, lesions were measured after resection. Pathological volumes and maximal diameters were then compared with the results of the segmentation algorithms.

RESULTS

A total of 20 lesions were analyzed. For all algorithms, segmented volumes correlated well with pathological volumes. In general, the threshold-based volumes exhibited a tendency to be smaller than the radiomics-based volumes. For all lesions, conventional threshold-based segmentation produced coefficients of variation which corresponded best with pathologically based volumes; however, for lesions larger than 3 ccm, the algorithm based on Local Entropy performed best, with a significantly better coefficient of variation (p = 0.0002) than the threshold-based algorithm.

CONCLUSIONS

We found that, for small lesions, results obtained using conventional threshold-based segmentation compared well with pathological volumes. For lesions larger than 3 ccm, the novel algorithm based on Local Entropy performed best. These findings confirm the results of our previous phantom studies. This algorithm is therefore worthy of inclusion in future studies for further confirmation and application.

Deep learning generation of preclinical positron emission tomography (PET) images from low-count PET with task-based performance assessment

BACKGROUND

Preclinical low-count positron emission tomography (LC-PET) imaging offers numerous advantages such as facilitating imaging logistics, enabling longitudinal studies of long- and short-lived isotopes as well as increasing scanner throughput. However, LC-PET is characterized by reduced photon-count levels resulting in low signal-to-noise ratio (SNR), segmentation difficulties, and quantification uncertainties.

PURPOSE

We developed and evaluated a novel deep-learning (DL) architecture-Attention based Residual-Dilated Net (ARD-Net)-to generate standard-count PET (SC-PET) images from LC-PET images. The performance of the ARD-Net framework was evaluated for numerous low count realizations using fidelity-based qualitative metrics, task-based segmentation, and quantitative metrics.

METHOD

Patient Derived tumor Xenograft (PDX) with tumors implanted in the mammary fat-pad were subjected to preclinical [18F]-Fluorodeoxyglucose (FDG)-PET/CT imaging. SC-PET images were derived from a 10 min static FDG-PET acquisition, 50 min post administration of FDG, and were resampled to generate four distinct LC-PET realizations corresponding to 10%, 5%, 1.6%, and 0.8% of SC-PET count-level. ARD-Net was trained and optimized using 48 preclinical FDG-PET datasets, while 16 datasets were utilized to assess performance. Further, the performance of ARD-Net was benchmarked against two leading DL-based methods (Residual UNet, RU-Net; and Dilated Network, D-Net) and non-DL methods (Non-Local Means, NLM; and Block Matching 3D Filtering, BM3D). The performance of the framework was evaluated using traditional fidelity-based image quality metrics such as Structural Similarity Index Metric (SSIM) and Normalized Root Mean Square Error (NRMSE), as well as human observer-based tumor segmentation performance (Dice Score and volume bias) and quantitative analysis of Standardized Uptake Value (SUV) measurements. Additionally, radiomics-derived features were utilized as a measure of quality assurance (QA) in comparison to true SC-PET. Finally, a performance ensemble score (EPS) was developed by integrating fidelity-based and task-based metrics. Concordance Correlation Coefficient (CCC) was utilized to determine concordance between measures. The non-parametric Friedman Test with Bonferroni correction was used to compare the performance of ARD-Net against benchmarked methods with significance at adjusted p-value ≤0.01.

RESULTS

ARD-Net-generated SC-PET images exhibited significantly better (p ≤ 0.01 post Bonferroni correction) overall image fidelity scores in terms of SSIM and NRMSE at majority of photon-count levels compared to benchmarked DL and non-DL methods. In terms of task-based quantitative accuracy evaluated by SUVMean and SUVPeak, ARD-Net exhibited less than 5% median absolute bias for SUVMean compared to true SC-PET and lower degree of variability compared to benchmarked DL and non-DL based methods in generating SC-PET. Additionally, ARD-Net-generated SC-PET images displayed higher degree of concordance to SC-PET images in terms of radiomics features compared to non-DL and other DL approaches. Finally, the ensemble score suggested that ARD-Net exhibited significantly superior performance compared to benchmarked algorithms (p ≤ 0.01 post Bonferroni correction).

CONCLUSION

ARD-Net provides a robust framework to generate SC-PET from LC-PET images. ARD-Net generated SC-PET images exhibited superior performance compared other DL and non-DL approaches in terms of image-fidelity based metrics, task-based segmentation metrics, and minimal bias in terms of task-based quantification performance for preclinical PET imaging.

Principal Component Analysis Applied to Radiomics Data: Added Value for Separating Benign from Malignant Solitary Pulmonary Nodules

Here, we report on the added value of principal component analysis applied to a dataset of texture features derived from 39 solitary pulmonary lung nodule (SPN) lesions for the purpose of differentiating benign from malignant lesions, as compared to the use of SUVmax alone. Texture features were derived using the LIFEx software. The eight best-performing first-, second-, and higher-order features for separating benign from malignant nodules, in addition to SUVmax (MaximumGreyLevelSUVbwIBSI184IY), were included for PCA. Two principal components (PCs) were retained, of which the contributions to the total variance were, respectively, 87.6% and 10.8%. When included in a logistic binomial regression analysis, including age and gender as covariates, both PCs proved to be significant predictors for the underlying benign or malignant character of the lesions under study (p = 0.009 for the first PC and 0.020 for the second PC). As opposed to SUVmax alone, which allowed for the accurate classification of 69% of the lesions, the regression model including both PCs allowed for the accurate classification of 77% of the lesions. PCs derived from PCA applied on selected texture features may allow for more accurate characterization of SPN when compared to SUVmax alone.

Utility of pre-treatment 18 F-fluorodeoxyglucose PET radiomic analysis in assessing nodal involvement in cervical cancer

OBJECTIVE

Intratumor heterogeneity has prognostic value in cervical cancer, which can be depicted on 18 F-fluorodeoxyglucose ( 18 F-FDG) PET/computed tomography (PET/CT) and then quantitatively characterized by texture features. This study aimed to evaluate the discriminative performance and predictive ability of the texture features in determining lymph node involvement in cervical cancer.

METHODS

A total of 101 patients with newly diagnosed cervical cancer, who underwent pre-treatment whole-body 18 F-FDG PET/CT imaging were retrospectively recruited. Patients were categorized based on their nodal status. Thirty-five radiomic features together with the maximum standardized uptake value (SUVmax), metabolic tumor volume (MTV) and total lesion glycolysis (TLG) of the primary cervical tumors were extracted. Conventional indices were used to build logistic regression model and texture features were used to build random forest model. The performances for differentiating nodal status were assessed by receiver operating characteristic analysis.

RESULTS

Conventional PET indices were significantly higher in patients with nodal involvement compared to those without: SUVmax = 14.22 vs. 10.05; MTV = 57.02 vs. 28.73; TLG = 492.8 vs. 188.8 ( P  < 0.05). Nineteen radiomic features describing regional heterogeneity were significantly different between nodal involvements. Area under the curves of the models with conventional indices and PET texture features for discriminating nodal status were 0.72 and 0.76, respectively.

CONCLUSION

PET-derived radiomic features had moderate performance in discriminating nodal involvement in cervical cancer; and they did not outperform model based on conventional indices.

Prediction of pathological response after neoadjuvant chemotherapy using baseline FDG PET heterogeneity features in breast cancer

Complete pathological response to neoadjuvant systemic treatment (NAST) in some subtypes of breast cancer (BC) has been used as a surrogate of long-term outcome. The possibility of predicting BC pathological response to NAST based on the baseline 18F-Fluorodeoxyglucose positron emission tomography (FDG PET), without the need of an interim study, is a focus of recent discussion. This review summarises the characteristics and results of the available studies regarding the potential impact of heterogeneity features of the primary tumour burden on baseline FDG PET in predicting pathological response to NAST in BC patients. Literature search was conducted on PubMed database and relevant data from each selected study were collected. A total of 13 studies were eligible for inclusion, all of them published over the last 5 years. Eight out of 13 analysed studies indicated an association between FDG PET-based tumour uptake heterogeneity features and prediction of response to NAST. When features associated with predicting response to NAST were derived, these varied between studies. Therefore, definitive reproducible findings across series were difficult to establish. This lack of consensus may reflect the heterogeneity and low number of included series. The clinical relevance of this topic justifies further investigation about the predictive role of baseline FDG PET.

A Decision Support System for the Identification of Metastases of Metastatic Melanoma Using Whole-Body FDG PET/CT Images

Metastatic Melanoma (MM) is an aggressive type of cancer which produces metastases throughout the body with very poor survival rates. Recent advances in immunotherapy have shown promising results for controlling disease's progression. Due to the often rapid progression, fast and accurate diagnosis and treatment response assessment is vital for the whole patient management. These procedures prerequisite accurate, whole-body tumor identification. This can be offered by the imaging modality Positron Emission Tomography (PET)/Computed Tomography (CT) with the radiotracer F 18-Fluorodeoxyglucose (FDG). However, manual segmentation of PET/CT images is a very time-consuming and labor intensive procedure that requires expert knowledge. Most of the previously published segmentation techniques focus on a specific type of tumor or part of the body and require a great amount of manually labeled data, which is, however, difficult for MM. Multimodal analysis of PET/CT is also crucial because FDG-PET contains only the functional information of tumors which can be complemented by the anatomical information of CT. In this paper, we propose a whole-body segmentation framework capable of efficiently identifying the highly heterogeneous tumor lesions of MM from the whole-body 3D FDG-PET/CT images. The proposed decision support system begins with an Ensemble Unsupervised Segmentation of regions of high FDG-uptake based on Fuzzy C-means and a custom region growing algorithm. Then, a region classification model based on radiomics features and Neural Networks classifies these regions as tumors or not. Experimental results showed high performance in the identification of MM lesions with Sensitivity 83.68%, Specificity 91.82%, F1-score 75.42%, AUC 94.16% and Balanced accuracy 87.75% which were also supported by the public dataset evaluation.

MRI radiomics combined with clinicopathologic features to predict disease-free survival in patients with early-stage cervical cancer

OBJECTIVE

To establish a comprehensive model including MRI radiomics and clinicopathological features to predict post-operative disease-free survival (DFS) in early-stage (pre-operative FIGO Stage IB-IIA) cervical cancer.

METHODS

A total of 183 patients with early-stage cervical cancer admitted to our Jiangsu Province Hospital underwent radical hysterectomy were enrolled in this retrospective study from January 2013 to June 2018 and their clinicopathology and MRI information were collected. They were then divided into training cohort (n = 129) and internal validation cohort (n = 54). The radiomic features were extracted from the pre-operative T1 contrast-enhanced (T1CE) and T2 weighted image of each patient. Least absolute shrinkage and selection operator regression and multivariate Cox proportional hazard model were used for feature selection, and the rad-score (RS) of each patient were evaluated individually. The clinicopathology model, T1CE_RS model, T1CE + T2_RS model, and clinicopathology combined with T1CE_RS model were established and compared. Patients were divided into high- and low-risk groups according to the optimum cut-off values of four models.

RESULTS

T1CE_RS model showed better performance on DFS prediction of early-stage cervical cancer than clinicopathological model (C-index: 0.724 vs 0.659). T1CE+T2_RS model did not improve predictive performance (C-index: 0.671). The combination of T1CE_RS and clinicopathology features showed more accurate predictive ability (C-index=0.773).

CONCLUSION

The combination of T1CE_RS and clinicopathology features showed more accurate predictive performance for DFS of patients with early-stage (pre-operative IB-IIA) cervical cancer which can aid in the design of individualised treatment strategies and regular follow-up.

ADVANCES IN KNOWLEDGE

A radiomics signature composed of T1CE radiomic features combined with clinicopathology features allowed differentiating patients at high or low risk of recurrence.

Nasopharyngeal Carcinoma Radiomic Evaluation with Serial PET/CT: Exploring Features Predictive of Survival in Patients with Long-Term Follow-Up

PURPOSE

We aim determine the value of PET and CT radiomic parameters on survival with serial follow-up PET/CT in patients with nasopharyngeal carcinoma (NPC) for which curative intent therapy is undertaken.

METHODS

Patients with NPC and available pre-treatment as well as follow up PET/CT were included from 2005 to 2006 and were followed to 2021. Baseline demographic, radiological and outcome data were collected. Univariable Cox proportional hazard models were used to evaluate features from baseline and follow-up time points, and landmark analyses were performed for each time point.

RESULTS

Sixty patients were enrolled, and two-hundred and seventy-eight (278) PET/CT were at baseline and during follow-up. Thirty-eight percent (38%) were female, and sixty-two patients were male. All patients underwent curative radiation or chemoradiation therapy. The median follow-up was 11.72 years (1.26-14.86). Five-year and ten-year overall survivals (OSs) were 80.0% and 66.2%, and progression-free survival (PFS) was 90.0% and 74.4%. Time-dependent modelling suggested that, among others, PET gray-level zone length matrix (GLZLM) gray-level non-uniformity (GLNU) (HR 2.74 95% CI 1.06, 7.05) was significantly associated with OS. Landmark analyses suggested that CT parameters were most predictive at 15 month, whereas PET parameters were most predictive at time points 3, 6, 9 and 15 month.

CONCLUSIONS

This study with long-term follow up data on NPC suggests that mainly PET-derived radiomic features are predictive for OS but not PFS in a time-dependent evaluation. Furthermore, CT radiomic measures may predict OS and PFS best at initial and long-term follow-up time points and PET measures may be more predictive in the interval. These modalities are commonly used in NPC surveillance, and prospective validation should be considered.

The efficacy of 18F-FDG-PET-based radiomic and deep-learning features using a machine-learning approach to predict the pathological risk subtypes of thymic epithelial tumors

OBJECTIVE

To examine whether the machine-learning approach using 18-fludeoxyglucose positron emission tomography (18F-FDG-PET)-based radiomic and deep-learning features is useful for predicting the pathological risk subtypes of thymic epithelial tumors (TETs).

METHODS

This retrospective study included 79 TET [27 low-risk thymomas (types A, AB and B1), 31 high-risk thymomas (types B2 and B3) and 21 thymic carcinomas] patients who underwent pre-therapeutic 18F-FDG-PET/CT. High-risk TETs (high-risk thymomas and thymic carcinomas) were 52 patients. The 107 PET-based radiomic features, including SUV-related parameters [maximum SUV (SUVmax), metabolic tumor volume (MTV), and total lesion glycolysis (TLG)] and 1024 deep-learning features extracted from the convolutional neural network were used to predict the pathological risk subtypes of TETs using six different machine-learning algorithms. The area under the curves (AUCs) were calculated to compare the predictive performances.

RESULTS

SUV-related parameters yielded the following AUCs for predicting thymic carcinomas: SUVmax 0.713, MTV 0.442, and TLG 0.479 or high-risk TETs: SUVmax 0.673, MTV 0.533, and TLG 0.539. The best-performing algorithm was the logistic regression model for predicting thymic carcinomas (AUC 0.900, accuracy 81.0%), and the random forest (RF) model for high-risk TETs (AUC 0.744, accuracy 72.2%). The AUC was significantly higher in the logistic regression model than three SUV-related parameters for predicting thymic carcinomas, and in the RF model than MTV and TLG for predicting high-risk TETs (each; p < 0.05).

CONCLUSION

18F-FDG-PET-based radiomic analysis using a machine-learning approach may be useful for predicting the pathological risk subtypes of TETs.

ADVANCES IN KNOWLEDGE

Machine-learning approach using 18F-FDG-PET-based radiomic features has the potential to predict the pathological risk subtypes of TETs.

Discrimination of Tumor Texture Based on MRI Radiomic Features: Is There a Volume Threshold? A Phantom Study

Radiomics is emerging as a promising tool to extract quantitative biomarkers—called radiomic features—from medical images, potentially contributing to the improvement in diagnosis and treatment of oncological patients. However, technical limitations might impair the reliability of radiomic features and their ability to quantify clinically relevant tissue properties. Among these, sampling the image signal in a too-small region can reduce the ability to discriminate tissues with different properties. However, a volume threshold guaranteeing a reliable analysis, which might vary according to the imaging modality and clinical scenario, has not been assessed yet. In this study, an MRI phantom specifically developed for radiomic investigation of gynecological malignancies was used to explore how the ability of radiomic features to discriminate different image textures varies with the volume of the analyzed region. The phantom, embedding inserts with different textures, was scanned on two 1.5T and one 3T scanners, each using the T2-weighted sequence of the clinical protocol implemented for gynecological studies. Within each of the three inserts, six cylindrical regions were drawn with volumes ranging from 0.8 cm3 to 29.8 cm3, and 944 radiomic features were extracted from both original images and from images processed with different filters. For each scanner, the ability of each feature to discriminate the different textures was quantified. Despite differences observed among the scanner models, the overall percentage of discriminative features across scanners was >70%, with the smallest volume having the lowest percentage of discriminative features for all scanners. Stratification by feature class, still aggregating data for original and filtered images, showed statistical significance for the association between the percentage of discriminative features with VOI sizes for features classes GLCM, GLDM, and GLSZM on the first 1.5T scanner and for first-order and GLSZM classes on the second 1.5T scanner. Poorer results in terms of features’ discriminative ability were found for the 3T scanner. Focusing on original images only, the analysis of discriminative features stratified by feature class showed that the first-order and GLCM were robust to VOI size variations (>85% discriminative features for all sizes), while for the 1.5T scanners, the GLSZM and NGTDM feature classes showed a percentage of discriminative features >80% only for volumes no smaller than 3.3 cm3, and equal or larger than 7.4 cm3 for the GLRLM. As for the 3T scanner, only the GLSZM showed a percentage of discriminative features >80% for all volume sizes above 3.3 cm3. Analogous considerations were obtained for each filter, providing useful indications for feature selection in this clinical case. Similar studies should be replicated with suitably adapted phantoms to derive useful data for other clinical scenarios and imaging modalities.

Pretherapy 18F-fluorodeoxyglucose positron emission tomography/computed tomography robust radiomic features predict overall survival in non-small cell lung cancer

OBJECTIVE

To extract robust radiomic features from staging positron emission tomography/computed tomography (18F- fluroodeoxyglucose PET/CT) in patients with non-small cell lung cancer from different segmentation methods and to assess their association with 2-year overall survival.

METHODS

Eighty-one patients with stage I-IV non-small cell lung cancer were included. All patients underwent a pretherapy 18F-FDG PET/CT. Primary tumors were delineated using four different segmentation methods: method 1, manual; method 2: manual with peripheral 1 mm erosion; method 3: absolute threshold at standardized uptake value (SUV) 2.5; and method 4: relative threshold at 40% SUVmax. Radiomic features from each method were extracted using Image Biomarker Standardization Initiative-compliant process. The study cohort was divided into two groups (exploratory and testing) in a ratio of 1:2 (n = 25 and n = 56, respectively). Exploratory cohort was used to identify robust radiomic features, defined as having a minimum concordance correlation coefficient ≥0.75 among all the 4-segmentation methods. The resulting texture features were evaluated for association with 2-year overall survival in the testing cohort (n = 56). All patients in the testing cohort had a follow-up for 2 years from the date of staging 18F-FDG PET/CT scan or till death. Cox proportional hazard models were used to evaluate the independent prognostic factors.

RESULTS

Exploratory and validation cohorts were equivalent regarding their basic characteristics (age, sex, and tumor stage). Ten radiomic features were deemed robust to the described four segmentation methods: SUV SD, SUVmax, SUVQ3, SUVpeak in 0.5 ml, total lesion glycolysis, histogram entropy log 2, histogram entropy log 10, histogram energy uniformity, gray level run length matrix-gray level non-uniformity, and gray level zone length matrix-gray level non-uniformity. At the end of 2-year follow-up, 41 patients were dead and 15 were still alive (overall survival = 26.8%; median survival = 14.7 months, 95% confidence interval: 10.2-19.2 months). Three texture features, regardless the segmentation method, were associated with 2-year overall survival: total lesion glycolysis, gray level run length matrix_gray level non-uniformity, and gray level zone length matrix_run-length non-uniformity. In the final Cox-regression model: total lesion glycolysis, and gray level zone length matrix_gray level non-uniformity were independent prognostic factors. The quartiles from the two features were combined with clinical staging in a prognostic model that allowed better risk stratification of patients for overall survival.

CONCLUSION

Ten radiomic features were robust to segmentation methods and two of them (total lesion glycolysis and gray level zone length matrix_gray level non-uniformity) were independently associated with 2-year overall survival. Together with the clinical staging, these features could be utilized towards improved risk stratification of lung cancer patients.

A review on advances in 18F-FDG PET/CT radiomics standardisation and application in lung disease management

Radiomics analysis quantifies the interpolation of multiple and invisible molecular features present in diagnostic and therapeutic images. Implementation of 18-fluorine-fluorodeoxyglucose positron emission tomography/computed tomography (¹⁸F-FDG PET/CT) radiomics captures various disorders in non-invasive and high-throughput manner. ¹⁸F-FDG PET/CT accurately identifies the metabolic and anatomical changes during cancer progression. Therefore, the application of ¹⁸F-FDG PET/CT in the field of oncology is well established. Clinical application of ¹⁸F-FDG PET/CT radiomics in lung infection and inflammation is also an emerging field. Combination of bioinformatics approaches or textual analysis allows radiomics to extract additional information to predict cell biology at the micro-level. However, radiomics texture analysis is affected by several factors associated with image acquisition and processing. At present, researchers are working on mitigating these interrupters and developing standardised workflow for texture biomarker establishment. This review article focuses on the application of ¹⁸F-FDG PET/CT in detecting lung diseases specifically on cancer, infection and inflammation. An overview of different approaches and challenges encountered on standardisation of ¹⁸F-FDG PET/CT technique has also been highlighted. The review article provides insights about radiomics standardisation and application of ¹⁸F-FDG PET/CT in lung disease management.

Radiomics in Triple Negative Breast Cancer: New Horizons in an Aggressive Subtype of the Disease

In the last decade, the analysis of the medical images has evolved significantly, applications and tools capable to extract quantitative characteristics of the images beyond the discrimination capacity of the investigator's eye being developed. The applications of this new research field, called radiomics, presented an exponential growth with direct implications in the diagnosis and prediction of response to therapy. Triple negative breast cancer (TNBC) is an aggressive breast cancer subtype with a severe prognosis, despite the aggressive multimodal treatments applied according to the guidelines. Radiomics has already proven the ability to differentiate TNBC from fibroadenoma. Radiomics features extracted from digital mammography may also distinguish between TNBC and non-TNBC. Recent research has identified three distinct subtypes of TNBC using IRM breast images voxel-level radiomics features (size/shape related features, texture features, sharpness). The correlation of these TNBC subtypes with the clinical response to neoadjuvant therapy may lead to the identification of biomarkers in order to guide the clinical decision. Furthermore, the variation of some radiomics features in the neoadjuvant settings provides a tool for the rapid evaluation of treatment efficacy. The association of radiomics features with already identified biomarkers can generate complex predictive and prognostic models. Standardization of image acquisition and also of radiomics feature extraction is required to validate this method in clinical practice.

Measuring Heterogeneity in 18F-Fluorodeoxyglucose Positron Emission Tomography Images for Classifying Metastatic and Benign Bone Lesions in Patients with Cervical Cancer

Purpose

Heterogeneity assessment can be applied for medical imaging analysis. Here, we evaluated first-order and texture analysis (TA) metrics in 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET) imaging for classification of metastatic and benign bone lesions in patients with cervical cancer.

Methods

The data of 18F-FDG PET studies performed on a specific PET/CT system from 2016 to 2018 in patients with cervical cancer were retrieved. The data of bone lesions extracted from studies over 2016–2017 and 2018 were used as training and validation datasets, respectively. Metastatic bone lesions were identified in each dataset, with an equal number of benign bone lesions selected. Cuboid volume of interest (VOI) consisting of 3 × 3 × 5 reconstructed voxels was applied for first-order metrics, and cubic VOI consisting of smaller voxels with trilinear interpolation of standardized uptake value (SUV) was adopted for TA metrics. First-order metrics included the maximum SUV (SUVmax) of lesions and the mean voxel SUV and its standard deviation (SUVsd), skewness, and kurtosis in VOI. In total, 4464 TA metrics based on 62 texture features were evaluated. Logistic regression was used for classification with area under the receiver operating characteristic curve (AUC) as the performance measure.

Results

From the training and validation datasets, 98 and 42 metastatic bone lesions were identified, respectively. SUVsd demonstrated higher performance than did SUVmax in both the training (AUC .798 vs .732, P = .001) and validation (AUC .786 vs .684, P < .001) datasets. Top-performing TA metrics demonstrated significantly higher performance in the training dataset, but not in the validation dataset.

Conclusion

A simple first-order measure of heterogeneity, SUVsd, was found to be superior to SUVmax for the classification of metastatic and benign bone lesions. Multiple hypothesis testing can result in false-positive findings in TA with multiple features and parameters; careful validation is required.

Delta radiomics: a systematic review

BACKGROUND

Radiomics can provide quantitative features from medical imaging that can be correlated with various biological features and clinical endpoints. Delta radiomics, on the other hand, consists in the analysis of feature variation at different acquisition time points, usually before and after therapy. The aim of this study was to provide a systematic review of the different delta radiomics approaches.

METHODS

Eligible articles were searched in Embase, PubMed, and ScienceDirect using a search string that included free text and/or Medical Subject Headings (MeSH) with three key search terms: "radiomics", "texture", and "delta". Studies were analysed using QUADAS-2 and the RQS tool.

RESULTS

Forty-eight studies were finally included. The studies were divided into preclinical/methodological (five studies, 10.4%); rectal cancer (six studies, 12.5%); lung cancer (twelve studies, 25%); sarcoma (five studies, 10.4%); prostate cancer (three studies, 6.3%), head and neck cancer (six studies, 12.5%); gastrointestinal malignancies excluding rectum (seven studies, 14.6%), and other disease sites (four studies, 8.3%). The median RQS of all studies was 25% (mean 21% ± 12%), with 13 studies (30.2%) achieving a quality score < 10% and 22 studies (51.2%) < 25%.

CONCLUSIONS

Delta radiomics shows potential benefit for several clinical endpoints in oncology (differential diagnosis, prognosis and prediction of treatment response, and evaluation of side effects). Nevertheless, the studies included in this systematic review suffer from the bias of overall low quality, so that the conclusions are currently heterogeneous, not robust, and not replicable. Further research with prospective and multicentre studies is needed for the clinical validation of delta radiomics approaches.

Radiomics in PET Imaging:: A Practical Guide for Newcomers

Radiomics has undergone considerable development in recent years. In PET imaging, very promising results concerning the ability of handcrafted features to predict the biological characteristics of lesions and to assess patient prognosis or response to treatment have been reported in the literature. This article presents a checklist for designing a reliable radiomic study, gives an overview of the steps of the pipeline, and outlines approaches for data harmonization. Tips are provided for critical reading of the content of articles. The advantages and limitations of handcrafted radiomics compared with deep-learning approaches for the characterization of PET images are also discussed.

Repeatability of image features extracted from FET PET in application to post-surgical glioblastoma assessment

Positron emission tomography (PET) imaging using the amino acid tracer O-[2-(¹⁸F)fluoroethyl]-L-tyrosine (FET) has gained increased popularity within the past decade in the management of glioblastoma (GBM). Radiomics features extracted from FET PET images may be sensitive to variations when imaging at multiple time points. It is therefore necessary to assess feature robustness to test-retest imaging. Eight patients with histologically confirmed GBM that had undergone post-surgical test-retest FET PET imaging were recruited. In total, 1578 radiomic features were extracted from biological tumour volumes (BTVs) delineated using a semi-automatic contouring method. Feature repeatability was assessed using the intraclass correlation coefficient (ICC). The effect of both bin width and filter choice on feature repeatability was also investigated. 59/106 (55.7%) features from the original image and 843/1472 (57.3%) features from filtered images had an ICC ≥ 0.85. Shape and first order features were most stable. Choice of bin width showed minimal impact on features defined as stable. The Laplacian of Gaussian (LoG, σ = 5 mm) and Wavelet filters (HLL and LHL) significantly improved feature repeatability (p ≪ 0.0001, p = 0.003, p = 0.002, respectively). Correlation of textural features with tumour volume was reported for transparency. FET PET radiomic features extracted from post-surgical images of GBM patients that are robust to test-retest imaging were identified. An investigation with a larger dataset is warranted to validate the findings in this study.

MRI-aided kernel PET image reconstruction method based on texture features

We investigate the reconstruction of low-count positron emission tomography (PET) projection, which is an important, but challenging, task. Using the texture feature extraction method of radiomics, i.e. the gray-level co-occurrence matrix (GLCM), texture features can be extracted from magnetic resonance imaging images with high-spatial resolution. In this work, we propose a kernel reconstruction method combining autocorrelation texture features derived from the GLCM. The new kernel function includes the correlations of both the intensity and texture features from the prior image. By regarding the GLCM as a discrete approximation of a probability density function, the asymptotically gray-level-invariant autocorrelation texture feature is generated, which can maintain the accuracy of texture features extracted from small image regions by reducing the number of quantized image gray levels. A computer simulation shows that the proposed method can effectively reduce the noise in the reconstructed image compared to the maximum likelihood expectation maximum method and improve the image quality and tumor region accuracy compared to the original kernel method for low-count PET reconstruction. A simulation study on clinical patient images also shows that the proposed method can improve the whole image quality and that the reconstruction of a high-uptake lesion is more accurate than that achieved by the original kernel method.

Quantitative radiomics features in diffuse large B-cell lymphoma: does segmentation method matter?

INTRODUCTION

Radiomics features may predict outcome in diffuse large B-cell lymphoma (DLBCL). Currently, multiple segmentation methods are used to calculate metabolic tumor volume (MTV). We assessed the influence of segmentation method on the discriminative power of radiomics features in DLBCL for patient level and for the largest lesion. Methods: 50 baseline ¹⁸F-fluorodeoxyglucose positron emission tomography computed tomography (PET/CT) scans of DLBCL patients who progressed or relapsed within 2 years after diagnosis were matched on uptake time and reconstruction method with 50 baseline PET/CT scans of DLBCL patients without progression. Scans were analysed using 6 semi-automatic segmentation methods (standardized uptake value (SUV)4.0, SUV2.5, 41% of the maximum SUV, 50% of the SUVpeak, majority vote (MV)2 and MV3, respectively). Based on these segmentations, 490 radiomics features were extracted at patient level and 486 features for the largest lesion. To quantify the agreement between features extracted from different segmentation methods, the intra-class correlation (ICC) agreement was calculated for each method compared to SUV4.0. The feature space was reduced by deleting features that had high Pearson correlations (≥0.7) with the previously established predictors MTV and/or SUVpeak. Model performance was assessed using stratified repeated cross-validation with 5 folds and 2000 repeats yielding the mean receiver-operating characteristics curve integral (CV-AUC) for all segmentation methods using logistic regression with backward feature selection. Results: The percentage of features yielding an ICC ≥0.75 compared to the SUV4.0 segmentation was lowest for A50P both at patient level and for the largest lesion, with 77.3% and 66.7% of the features yielding an ICC ≥0.75, respectively. Features were not highly correlated with MTV, with at least 435 features at patient level and 409 features for the largest lesion for all segmentation methods with a correlation coefficient <0.7. Features were highly correlated with SUVpeak (at least 190 and 134 were uncorrelated, respectively). CV-AUCs ranged between 0.69±0.11 and 0.84±0.09 for patient level, and between 0.69±0.11 and 0.73±0.10 for lesion level. Conclusion: Even though there are differences in the actual radiomics feature values derived and selected features between segmentation methods, there is no substantial difference in the discriminative power of radiomics features between segmentation methods.

Experimental phantom evaluation to identify robust positron emission tomography (PET) radiomic features

Background

Radiomics analysis usually involves, especially in multicenter and large hospital studies, different imaging protocols for acquisition, reconstruction, and processing of data. Differences in protocols can lead to differences in the quantification of the biomarker distribution, leading to radiomic feature variability. The aim of our study was to identify those radiomic features robust to the different degrading factors in positron emission tomography (PET) studies. We proposed the use of the standardized measurements of the European Association Research Ltd. (EARL) accreditation to retrospectively identify the radiomic features having low variability to the different systems and reconstruction protocols. In addition, we presented a reproducible procedure to identify PET radiomic features robust to PET/CT imaging metal artifacts. In 27 heterogeneous homemade phantoms for which ground truth was accurately defined by CT segmentation, we evaluated the segmentation accuracy and radiomic feature reliability given by the contrast-oriented algorithm (COA) and the 40% threshold PET segmentation. In the comparison of two data sets, robustness was defined by Wilcoxon rank tests, bias was quantified by Bland–Altman (BA) plot analysis, and strong correlations were identified by Spearman correlation test (r > 0.8 and p satisfied multiple test Bonferroni correction).

Results

Forty-eight radiomic features were robust to system, 22 to resolution, 102 to metal artifacts, and 42 to different PET segmentation tools. Overall, only 4 radiomic features were simultaneously robust to all degrading factors. Although both segmentation approaches significantly underestimated the volume with respect to the ground truth, with relative deviations of −62 ± 36% for COA and −50 ± 44% for 40%, radiomic features derived from the ground truth were strongly correlated and/or robust to 98 radiomic features derived from COA and to 102 from 40%.

Conclusion

In multicenter studies, we recommend the analysis of EARL accreditation measurements in order to retrospectively identify the robust PET radiomic features. Furthermore, 4 radiomic features (area under the curve of the cumulative SUV volume histogram, skewness, kurtosis, and gray-level variance derived from GLRLM after application of an equal probability quantization algorithm on the voxels within lesion) were robust to all degrading factors. In addition, the feasibility of 40% and COA segmentations for their use in radiomics analysis has been demonstrated.

Supplementary Information

The online version contains supplementary material available at 10.1186/s40658-021-00390-7.

Preoperative prediction of regional lymph node metastasis of colorectal cancer based on 18F-FDG PET/CT and machine learning

PURPOSE

To establish and validate a regional lymph node (LN) metastasis prediction model of colorectal cancer (CRC) based on 18F-FDG PET/CT and radiomic features using machine-learning methods.

METHODS

A total of 199 colorectal cancer patients underwent pre-therapy diagnostic 18F-FDG PET/CT scans and CRC radical surgery. The Chang-Gung Image Texture Analysis toolbox (CGITA) was used to extract 70 PET radiomic features reflecting 18F-FDG uptake heterogeneity of tumors. The least absolute shrinkage and selection operator (LASSO) algorithm was used to select radiomic features and develop a radiomic signature score (Rad-score). The training set was used to establish five machine-learning prediction models and the test set was used to test the efficacy of the models. The effectiveness of the models was compared by ROC analysis.

RESULTS

The CRC patients were divided into a training set (n = 144) and a test set (n = 55). Two radiomic features were selected to build the Rad-score. Five machine-learning algorithms including logistic regression, support vector machine (SVM), random forest, neural network and eXtreme gradient boosting (XGBoost) were used to established models. Among the five machine-learning models, logistic regression (AUC 0.866, 95% CI 0.808-0.925) and XGBoost (AUC 0.903, 95% CI 0.855-0.951) models performed the best. In the training set, the AUC of these two models were significantly higher than that of the LN metastasis status reported by 18F-FDG PET/CT for differentiating positive and negative regional LN metastases in CRC (all p < 0.05). Good efficacy of the above two models was also achieved in the test set. We created a nomogram based on the logistic regression model that visualized the results and provided an easy-to-use method for predicting regional LN metastasis in patients with CRC.

CONCLUSION

In this study, five machine-learning models for preoperative prediction of regional LN metastasis of CRC based on 18F-FDG PET/CT and PET-based radiomic features were successfully developed and validated. Among them, the logistic regression and XGBoost models performed the best, with higher efficacy than 18F-FDG PET/CT in both the training and test sets.

Relationship between tumor heterogeneity and volume in cervical cancer: Evidence from integrated fluorodeoxyglucose 18 PET/MR texture analysis

OBJECTIVE

The aim of this study was to evaluate the effect of cervical cancer volume on PET/magnetic resonance (MR) texture heterogeneity.

MATERIALS AND METHODS

We retrospectively analyzed the PET/MR images of 138 patients with pathologically diagnosed cervical squamous cell carcinoma, including 50 patients undergoing surgery and 88 patients receiving concurrent chemoradiotherapy. Fluorodeoxyglucose 18 (18FDG)-PET/MR examination were performed for each patient before treatment, and the PET and MR texture analysis were undertaken. The texture features of the tumor based on gray-level co-occurrence matrices were extracted, and the correlation between tumor texture features and volume parameters was analyzed using Spearman's rank correlation coefficient. Finally, the variation trend of tumor texture heterogeneity was analyzed as tumor volumes increased.

RESULTS

PET texture features were highly correlated with metabolic tumor volume (MTV), including entropy-log2, entropy-log10, energy, homogeneity, dissimilarity, contrast, correlation, and the correlation coefficients (rs) were 0.955, 0.955, -0.897, 0.883, -0.881, -0.876, and 0.847 (P < 0.001), respectively. In the range of smaller MTV, the texture heterogeneity of energy, entropy-log2, and entropy-log10 increases with an increase in tumor volume, whereas the texture heterogeneity of homogeneity, dissimilarity, contrast, and correlation decreases with an increase in tumor volume. Only homogeneity, contrast, correlation, and dissimilarity had high correlation with tumor volume on MRI. The correlation coefficients (rs) were 0.76, -0.737, 0.644, and -0.739 (P < 0.001), respectively. The texture heterogeneity of MRI features that are highly correlated with tumor volume decreases with increasing tumor volume.

CONCLUSION

In the small tumor volume range, the heterogeneity variation trend of PET texture features is inconsistent as the tumor volume increases, but the variation trend of MRI texture heterogeneity is consistent, and MRI texture heterogeneity decreases as tumor volume increases. These results suggest that MRI is a better imaging modality when compared with PET in determining tumor texture heterogeneity in the small tumor volume range.

Assessment of the Prognostic Value of Radiomic Features in 18F-FMISO PET Imaging of Hypoxia in Postsurgery Brain Cancer Patients: Secondary Analysis of Imaging Data from a Single-Center Study and the Multicenter ACRIN 6684 Trial

Hypoxia is associated with resistance to radiotherapy and chemotherapy in malignant gliomas, and it can be imaged by positron emission tomography with ¹⁸F-fluoromisonidazole (¹⁸F-FMISO). Previous results for patients with brain cancer imaged with ¹⁸F-FMISO at a single center before conventional chemoradiotherapy showed that tumor uptake via T/Bmax (tissue SUVmax/blood SUV) and hypoxic volume (HV) was associated with poor survival. However, in a multicenter clinical trial (ACRIN 6684), traditional uptake parameters were not found to be prognostically significant, but tumor SUVpeak did predict survival at 1 year. The present analysis considered both study cohorts to reconcile key differences and examine the potential utility of adding radiomic features as prognostic variables for outcome prediction on the combined cohort of 72 patients with brain cancer (30 University of Washington and 42 ACRIN 6684). We used both ¹⁸F-FMISO intensity metrics (T/Bmax, HV, SUV, SUVmax, SUVpeak) and assessed radiomic measures that determined first-order (histogram), second-order, and higher-order radiomic features of ¹⁸F-FMISO uptake distributions. A multivariate model was developed that included age, HV, and the intensity of ¹⁸F-FMISO uptake. HV and SUVpeak were both independent predictors of outcome for the combined data set (P < .001) and were also found significant in multivariate prognostic models (P < .002 and P < .001, respectively). Further model selection that included radiomic features showed the additional prognostic value for overall survival of specific higher order texture features, leading to an increase in relative risk prediction performance by a further 5%, when added to the multivariate clinical model..

Integration of PET/CT Radiomics and Semantic Features for Differentiation between Active Pulmonary Tuberculosis and Lung Cancer

PURPOSE

We aim to accurately differentiate between active pulmonary tuberculosis (TB) and lung cancer (LC) based on radiomics and semantic features as extracted from pre-treatment positron emission tomography/X-ray computed tomography (PET/CT) images.

PROCEDURES

A total of 174 patients (77/97 pulmonary TB/LC as confirmed by pathology) were retrospectively selected, with 122 in the training cohort and 52 in the validation cohort. Four hundred eighty-seven radiomics features were initially extracted to quantify phenotypic characteristics of the lesion region in both PET and CT images. Eleven semantic features were additionally defined by two experienced nuclear medicine physicians. Feature selection was performed in 5 steps to enable derivation of robust and effective signatures. Multivariable logistic regression analysis was subsequently used to develop a radiomics nomogram. The calibration, discrimination, and clinical usefulness of the nomogram were evaluated in both the training and independent validation cohorts.

RESULTS

The individualized radiomics nomogram, which combined PET/CT radiomics signature with semantic features, demonstrated good calibration and significantly improved the diagnostic performance with respect to the semantic model alone or PET/CT signature alone in training cohort (AUC 0.97 vs. 0.94 or 0.91, p = 0.0392 or 0.0056), whereas did not significantly improve the performance in validation cohort (AUC 0.93 vs. 0.89 or 0.91, p = 0.3098 or 0.3323).

CONCLUSION

The radiomics nomogram showed potential for individualized differential diagnosis between solid active pulmonary TB and solid LC, although the improvement of performance was not significant relative to semantic model.

A Systematic Review of PET Textural Analysis and Radiomics in Cancer

Background: Although many works have supported the utility of PET radiomics, several authors have raised concerns over the robustness and replicability of the results. This study aimed to perform a systematic review on the topic of PET radiomics and the used methodologies. Methods: PubMed was searched up to 15 October 2020. Original research articles based on human data specifying at least one tumor type and PET image were included, excluding those that apply only first-order statistics and those including fewer than 20 patients. Each publication, cancer type, objective and several methodological parameters (number of patients and features, validation approach, among other things) were extracted. Results: A total of 290 studies were included. Lung (28%) and head and neck (24%) were the most studied cancers. The most common objective was prognosis/treatment response (46%), followed by diagnosis/staging (21%), tumor characterization (18%) and technical evaluations (15%). The average number of patients included was 114 (median = 71; range 20–1419), and the average number of high-order features calculated per study was 31 (median = 26, range 1–286). Conclusions: PET radiomics is a promising field, but the number of patients in most publications is insufficient, and very few papers perform in-depth validations. The role of standardization initiatives will be crucial in the upcoming years.

Plausibility and redundancy analysis to select FDG-PET textural features in non-small cell lung cancer

Background

Radiomics refers to the extraction of a large number of image biomarker describing the tumor phenotype displayed in a medical image. Extracted from positron emission tomography (PET) images, radiomics showed diagnostic and prognostic value for several cancer types. However, a large number of radiomic features are nonreproducible or highly correlated with conventional PET metrics. Moreover, radiomic features used in the clinic should yield relevant information about tumor texture. In this study, we propose a framework to identify technical and clinical meaningful features and exemplify our results using a PET non‐small cell lung cancer (NSCLC) dataset.

Materials and methods

The proposed selection procedure consists of several steps. A priori, we only include features that were found to be reproducible in a multicenter setting. Next, we apply a voxel randomization step to identify features that reflect actual textural information, that is, that yield in 90% of the patient scans a value significantly different from random texture. Finally, the remaining features were correlated with standard PET metrics to further remove redundancy with common PET metrics. The selection procedure was performed for different volume ranges, that is, excluding lesions with smaller volumes in order to assess the effect of tumor size on the results. To exemplify our procedure, the selected features were used to predict 1‐yr survival in a dataset of 150 NSCLC patients. A predictive model was built using volume as predictive factor for smaller, and one of the selected features as predictive factor for bigger lesions. The prediction accuracy of the both models were compared with the prediction accuracy of volume.

Results

The number of selected features depended on the lesion size included in the analysis. When including the whole dataset, from 19 features reflecting actual texture only two were found to be not strongly correlated with conventional PET metrics. When excluding lesions smaller than 11.49 and 33.10 mL (25 and 50 percentile of the dataset), four out of 27 features and 13 out of 29 features remained after eliminating features highly correlated with standard PET metrics. When excluding lesions smaller than 103.9 mL (75 percentile), 33 out of 53 features remained. For larger lesions, some of these features outperformed volume in terms of classification accuracy (increase of 4–10%). The combination of using volume as predictor for smaller and one of the selected features for larger lesions also improved the accuracy when compared with volume only (increase from 72% to 76%).

Conclusion

When performing radiomic analysis for smaller lesions, it should be first carefully investigated if a textural feature reflects actual heterogeneity information. Next, verification of the absence of correlation with all conventional PET metrics is essential in order to assess the additional value of radiomic features. Radiomic analysis with lesions larger than 11.4 mL might give additional information to conventional metrics while at the same time reflecting actual tumor texture. Using a combination of volume and one of the selected features for prediction yields promise to increase accuracy and reliability of a radiomic model.

Advanced intra-tumoural structural characterisation of hepatocellular carcinoma utilising FDG-PET/CT: a comparative study of radiomics and metabolic features in 3D and 2D

PURPOSE

The aim of our work is to evaluate the correlation of two-dimensional (2D) and three-dimensional (3D) radiomics and metabolic features of hepatocellular carcinoma (HCC) with tumour diameter, staging, and metabolic tumour volume (MTV).

MATERIAL AND METHODS

Thirty-three patients with HCC were studied using 18F-fluorodeoxyglucose positron-emission tomography with computed tomography (18F [FDG] PET/CT). The tumours were segmented from the PET images after CT correction. Metabolic parameters and 35 radiomics features were compared using 2D and 3D modes. The metabolic parameters and tumour morphology were compared using 2 different types of software. Tumour heterogeneity was studied in both metabolic parameters and radiomics features. Finally, the correlation between the metabolic and radiomics features in 3D mode, as well as tumour morphology and staging according to the American Joint Committee on Cancer (AJCC) staging were studied.

RESULTS

Most of the metabolic parameters and radiomics features are statically stable through the 2D and 3D modes. Most of the 3D mode features show a correlation with metabolic parameters; the total lesion glycolysis (TLG) shows the highest correlation, with a Spearman correlation coefficient (rs) of 0.9776. Also, the grey level run length matrix/run length non-uniformity (GLRLM_RLNU) from radiomics features exhibits a correlation with a Spearman correlation coefficient of 0.9733. Maximum tumour diameter is correlated with TLG and GLRLM_RLNU, with rs equal to 0.7461 and 0.7143, respectively. Regarding AJCC staging, some features show a medium but prognostic correlation. In the case of 2D-mode features, all metabolic and radiomics features show no significant correlation with MTV, AJCC staging, and tumour maximum diameter.

CONCLUSIONS

Most of the normal metabolic parameters and radiomics features are statistically stable through the 3D and 2D modes. 3D radiomics features are significantly correlated with tumour volume, maximum diameter, and staging. Conversely, 2D features have negligible correlation with the same parameters. Therefore, 3D mode features are preferable and can accurately evaluate tumour heterogeneity.

A Phantom Study to Investigate Robustness and Reproducibility of Grey Level Co-Occurrence Matrix (GLCM)-Based Radiomics Features for PET

Quantification and classification of heterogeneous radiotracer uptake in Positron Emission Tomography (PET) using textural features (termed as radiomics) and artificial intelligence (AI) has the potential to be used as a biomarker of diagnosis and prognosis. However, textural features have been predicted to be strongly correlated with volume, segmentation and quantization, while the impact of image contrast and noise has not been assessed systematically. Further continuous investigations are required to update the existing standardization initiatives. This study aimed to investigate the relationships between textural features and these factors with 18F filled torso NEMA phantom to yield different contrasts and reconstructed with different durations to represent varying levels of noise. The phantom was also scanned with heterogeneous spherical inserts fabricated with 3D printing technology. All spheres were delineated using: (1) the exact boundaries based on their known diameters; (2) 40% fixed; and (3) adaptive threshold. Six textural features were derived from the gray level co-occurrence matrix (GLCM) using different quantization levels. The results indicate that homogeneity and dissimilarity are the most suitable for measuring PET tumor heterogeneity with quantization 64 provided that the segmentation method is robust to noise and contrast variations. To use these textural features as prognostic biomarkers, changes in textural features between baseline and treatment scans should always be reported along with the changes in volumes.

Tumor response prediction in 90Y radioembolization with PET-based radiomics features and absorbed dose metrics

Purpose

To evaluate whether lesion radiomics features and absorbed dose metrics extracted from post-therapy ⁹⁰Y PET can be integrated to better predict outcomes in microsphere radioembolization of liver malignancies

Methods

Given the noisy nature of ⁹⁰Y PET, first, a liver phantom study with repeated acquisitions and varying reconstruction parameters was used to identify a subset of robust radiomics features for the patient analysis. In 36 radioembolization procedures, ⁹⁰Y PET/CT was performed within a couple of hours to extract 46 radiomics features and estimate absorbed dose in 105 primary and metastatic liver lesions. Robust radiomics modeling was based on bootstrapped multivariate logistic regression with shrinkage regularization (LASSO) and Cox regression with LASSO. Nested cross-validation and bootstrap resampling were used for optimal parameter/feature selection and for guarding against overfitting risks. Spearman rank correlation was used to analyze feature associations. Area under the receiver-operating characteristics curve (AUC) was used for lesion response (at first follow-up) analysis while Kaplan-Meier plots and c-index were used to assess progression model performance. Models with absorbed dose only, radiomics only, and combined models were developed to predict lesion outcome.

Results

The phantom study identified 15/46 reproducible and robust radiomics features that were subsequently used in the patient models. A lesion response model with zone percentage (ZP) and mean absorbed dose achieved an AUC of 0.729 (95% CI 0.702–0.758), and a progression model with zone size nonuniformity (ZSN) and absorbed dose achieved a c-index of 0.803 (95% CI 0.790–0.815) on nested cross-validation (CV). Although the combined models outperformed the radiomics only and absorbed dose only models, statistical significance was not achieved with the current limited data set to establish expected superiority.

Conclusion

We have developed new lesion-level response and progression models using textural radiomics features, derived from ⁹⁰Y PET combined with mean absorbed dose for predicting outcome in radioembolization. These encouraging, but limited results, will need further validation in independent and larger datasets prior to any clinical adoption.

Supplementary Information

Supplementary information accompanies this paper at 10.1186/s40658-020-00340-9.

Is FDG-PET texture analysis related to intratumor biological heterogeneity in lung cancer?

OBJECTIVES

We aimed at investigating the origin of the correlations between tumor volume and ¹⁸F-FDG-PET texture indices in lung cancer.

METHODS

Eighty-five consecutive patients with newly diagnosed non-small cell lung cancer (NSCLC) underwent a ¹⁸F-FDG-PET/CT scan before treatment. Seven phantom spheres uniformly filled with ¹⁸F-FDG, and covering a range of activities and volumes similar to that found in lung tumors, were also scanned. Established texture indices were computed for lung tumors and homogeneous spheres. The dependence between textural indices and volume in homogeneous spheres was modeled and then used to predict texture indices in lung tumors. Correlation analyses were carried out between predicted and texture features measured in lung tumors. Cox proportional hazards regression was used to investigate the associations between overall survival and volume-adjusted textural features.

RESULTS

All textural features showed strong, non-linear correlations with volume, both in tumors and homogeneous spheres. Correlations between predicted versus measured texture features were very high for contrast (r² = 0.91), dissimilarity (r² = 0.90), ZP (r² = 0.90), GLNN (r² = 0.86), and homogeneity (r² = 0.82); high for entropy (r² = 0.50) and HILAE (r² = 0.53); and low for energy (r² = 0.30). Cox regressions showed that among volume-adjusted features, only HILAE was associated with overall survival (b = - 0.35, p = 0.008).

CONCLUSION

We have shown that texture indices previously found to be correlated with a number of clinically relevant outcomes might not provide independent information apart from that driven by their correlation with tumor volume, suggesting that these metrics might not be suitable as intratumor heterogeneity markers.

KEY POINTS

• Associations between texture FDG-PET indices and overall survival have been widely reported in lung cancer, with tumor volume also being associated with overall survival, and therefore, it is still unclear whether the predictive power of textural indices is simply driven by this correlation. • Our results demonstrated strong non-linear correlations between textural indices and volume, showing an analogous behavior for lung tumors from patients and homogeneous spheres inserted in phantoms. • Our findings showed that texture FDG-PET indices might not provide independent information apart from that driven by their correlation with tumor volume.

Radiomics in PET/CT: Current Status and Future AI-Based Evolutions

This short review aims at providing the readers with an update on the current status, as well as future perspectives in the quickly evolving field of radiomics applied to the field of PET/CT imaging. Numerous pitfalls have been identified in study design, data acquisition, segmentation, features calculation and modeling by the radiomics community, and these are often the same issues across all image modalities and clinical applications, however some of these are specific to PET/CT (and SPECT/CT) imaging and therefore the present paper focuses on those. In most cases, recommendations and potential methodological solutions do exist and should therefore be followed to improve the overall quality and reproducibility of published studies. In terms of future evolutions, the techniques from the larger field of artificial intelligence (AI), including those relying on deep neural networks (also known as deep learning) have already shown impressive potential to provide solutions, especially in terms of automation, but also to maybe fully replace the tools the radiomics community has been using until now in order to build the usual radiomics workflow. Some important challenges remain to be addressed before the full impact of AI may be realized but overall the field has made striking advances over the last few years and it is expected advances will continue at a rapid pace.

A Role for FDG PET Radiomics in Personalized Medicine?

Radiomics describes the extraction of multiple features from medical images, including molecular imaging modalities, that with bioinformatic approaches, provide additional clinically relevant information that may be invisible to the human eye. This information may complement standard radiological interpretation with data that may better characterize a disease or that may provide predictive or prognostic information. Progressing from predefined image features, often describing heterogeneity of voxel intensities within a volume of interest, there is increasing use of machine learning to classify disease characteristics and deep learning methods based on artificial neural networks that can learn features without a priori definition and without the need for preprocessing of images. There have been advances in standardization and harmonization of methods to a level that should support multicenter studies. However, in this relatively early phase of research in the field, there are limited aspects that have been adopted into routine practice. Most of the reports in the molecular imaging field describe radiomic approaches in cancer using 18F-fluorodeoxyglucose positron emission tomography (18F-FDG-PET). In this review, we will describe radiomics in molecular imaging and summarize the pertinent literature in lung cancer where reports are most prevalent and mature.

MRI-based radiomics signature for localized prostate cancer: a new clinical tool for cancer aggressiveness prediction? Sub-study of prospective phase II trial on ultra-hypofractionated radiotherapy (AIRC IG-13218)

OBJECTIVES

Radiomic involves testing the associations of a large number of quantitative imaging features with clinical characteristics. Our aim was to extract a radiomic signature from axial T2-weighted (T2-W) magnetic resonance imaging (MRI) of the whole prostate able to predict oncological and radiological scores in prostate cancer (PCa).

METHODS

This study included 65 patients with localized PCa treated with radiotherapy (RT) between 2014 and 2018. For each patient, the T2-W MRI images were normalized with the histogram intensity scale standardization method. Features were extracted with the IBEX software. The association of each radiomic feature with risk class, T-stage, Gleason score (GS), extracapsular extension (ECE) score, and Prostate Imaging Reporting and Data System (PI-RADS v2) score was assessed by univariate and multivariate analysis.

RESULTS

Forty-nine out of 65 patients were eligible. Among the 1702 features extracted, 3 to 6 features with the highest predictive power were selected for each outcome. This analysis showed that texture features were the most predictive for GS, PI-RADS v2 score, and risk class; intensity features were highly associated with T-stage, ECE score, and risk class, with areas under the receiver operating characteristic curve (ROC AUC) ranging from 0.74 to 0.94.

CONCLUSIONS

MRI-based radiomics is a promising tool for prediction of PCa characteristics. Although a significant association was found between the selected features and all the mentioned clinical/radiological scores, further validations on larger cohorts are needed before these findings can be applied in the clinical practice.

KEY POINTS

• A radiomic model was used to classify PCa aggressiveness. • Radiomic analysis was performed on T2-W magnetic resonance images of the whole prostate gland. • The most predictive features belong to the texture (57%) and intensity (43%) domains.

Characterization of FDG PET Images Using Texture Analysis in Tumors of the Gastro-Intestinal Tract: A Review

Radiomics or textural feature extraction obtained from positron emission tomography (PET) images through complex mathematical models of the spatial relationship between multiple image voxels is currently emerging as a new tool for assessing intra-tumoral heterogeneity in medical imaging. In this paper, available literature on texture analysis using FDG PET imaging in patients suffering from tumors of the gastro-intestinal tract is reviewed. While texture analysis of FDG PET images appears clinically promising, due to the lack of technical specifications, a large variability in the implemented methodology used for texture analysis and lack of statistical robustness, at present, no firm conclusions can be drawn regarding the predictive or prognostic value of FDG PET texture analysis derived indices in patients suffering from gastro-enterologic tumors. In order to move forward in this field, a harmonized image acquisition and processing protocol as well as a harmonized protocol for texture analysis of tumor volumes, allowing multi-center studies excluding statistical biases should be considered. Furthermore, the complementary and additional value of CT-imaging, as part of the PET/CT imaging technique, warrants exploration.

Metabolic radiogenomics in lung cancer: associations between FDG PET image features and oncogenic signaling pathway alterations

This study investigated the associations between image features extracted from tumor ¹⁸F-fluorodeoxyglucose (FDG) uptake and genetic alterations in patients with lung cancer. A total of 137 patients (age, 62.7 ± 10.2 years) who underwent FDG positron emission tomography/computed tomography (PET/CT) and targeted deep sequencing analysis for a tumor lesion, comprising 61 adenocarcinoma (ADC), 31 squamous cell carcinoma (SQCC), and 45 small cell lung cancer (SCLC) patients, were enrolled in this study. From the tumor lesions, 86 image features were extracted, and 381 genes were assessed. PET features were associated with genetic mutations: 41 genes with 24 features in ADC; 35 genes with 22 features in SQCC; and 43 genes with 25 features in SCLC (FDR < 0.05). Clusters based on PET features showed an association with alterations in oncogenic signaling pathways: Cell cycle and WNT signaling pathways in ADC (p = 0.023, p = 0.035, respectively); Cell cycle, p53, and WNT in SQCC (p = 0.045, 0.009, and 0.029, respectively); and TGFβ in SCLC (p = 0.030). In addition, SUV_peak and SUV_max were associated with a mutation of the TGFβ signaling pathway in ADC (FDR = 0.001, < 0.001). In this study, PET image features had significant associations with alterations in genes and oncogenic signaling pathways in patients with lung cancer.

Quantitative accuracy of radiomic features of low-dose 18F-FDG PET imaging

Background

¹⁸F-FDG PET based radiomics is promising for precision oncology imaging. This work aims to explore quantitative accuracies of radiomic features (RFs) for low-dose ¹⁸F-FDG PET imaging.

Methods

Twenty lung cancer patients were prospectively enrolled and underwent ¹⁸F-FDG PET/CT scans. Low-dose PET situations (true counts: 20×10⁶, 15×10⁶, 10×10⁶, 7.5×10⁶, 5×10⁶, 2×10⁶, 1×10⁶, 0.5×10⁶, 0.25×10⁶) were simulated by randomly discarding counts from the acquired list-mode data. Each PET image was created using the scanner default reconstruction parameters. Each lesion volume of interest (VOI) was obtained via an adaptive contouring method with a threshold of 50% peak standardized uptake value (SUVpeak) in the PET images with full count data and VOIs were copied to the PET images at the reduced count level. Conventional SUV measures, features calculated from first-order statistics (FOS) and texture features (TFs) were calculated. Texture based RF include features calculated from gray-level co-occurrence matrix (GLCM), gray-level run length matrix (GLRLM), gray-level size zone matrix (GLSZM), neighboring gray-level dependence matrix (NGLDM) and neighbor gray-tone difference matrix (NGTDM). Bias percentage (BP) at different count levels for each RF was calculated.

Results

Fifty-seven lesions with a volume greater than 1.5 cm³ were found (mean volume, 25.7 cm³, volume range, 1.5–245.4 cm³). In comparison with normal total counts, mean SUV (SUVmean) in the lesions, normal lungs and livers, Entropy and sum entropy from GLCM, busyness from NGTDM and run-length non-uniformity from GLRLM were the most robust features, with a BP of 5% at the count level of 1×10⁶ (equivalent to an effective dose of 0.04 mSv) RF including cluster shade from GLCM, long-run low grey-level emphasis, high grey-level run emphasis and short-run low grey-level emphasis from GLRM exhibited the worst performance with 50% of bias with 20×10⁶ counts (equivalent to an effective dose of 0.8 mSv).

Conclusions

In terms of the lesions included in this study, SUVmean, entropy and sum entropy from GLCM, busyness from NGTDM and run-length non-uniformity from GLRLM were the least sensitive features to lowering count.

Machine learning-based analysis of [18F]DCFPyL PET radiomics for risk stratification in primary prostate cancer

PURPOSE

Quantitative prostate-specific membrane antigen (PSMA) PET analysis may provide for non-invasive and objective risk stratification of primary prostate cancer (PCa) patients. We determined the ability of machine learning-based analysis of quantitative [¹⁸F]DCFPyL PET metrics to predict metastatic disease or high-risk pathological tumor features.

METHODS

In a prospective cohort study, 76 patients with intermediate- to high-risk PCa scheduled for robot-assisted radical prostatectomy with extended pelvic lymph node dissection underwent pre-operative [¹⁸F]DCFPyL PET-CT. Primary tumors were delineated using 50-70% peak isocontour thresholds on images with and without partial-volume correction (PVC). Four hundred and eighty standardized radiomic features were extracted per tumor. Random forest models were trained to predict lymph node involvement (LNI), presence of any metastasis, Gleason score ≥ 8, and presence of extracapsular extension (ECE). For comparison, models were also trained using standard PET features (SUVs, volume, total PSMA uptake). Model performance was validated using 50 times repeated 5-fold cross-validation yielding the mean receiver-operator characteristic curve AUC.

RESULTS

The radiomics-based machine learning models predicted LNI (AUC 0.86 ± 0.15, p < 0.01), nodal or distant metastasis (AUC 0.86 ± 0.14, p < 0.01), Gleason score (0.81 ± 0.16, p < 0.01), and ECE (0.76 ± 0.12, p < 0.01). The highest AUCs reached using standard PET metrics were lower than those of radiomics-based models. For LNI and metastasis prediction, PVC and a higher delineation threshold improved model stability. Machine learning pre-processing methods had a minor impact on model performance.

CONCLUSION

Machine learning-based analysis of quantitative [¹⁸F]DCFPyL PET metrics can predict LNI and high-risk pathological tumor features in primary PCa patients. These findings indicate that PSMA expression detected on PET is related to both primary tumor histopathology and metastatic tendency. Multicenter external validation is needed to determine the benefits of using radiomics versus standard PET metrics in clinical practice.

Current status and quality of radiomics studies in lymphoma: a systematic review

OBJECTIVES

To perform a systematic review regarding the developments in the field of radiomics in lymphoma. To evaluate the quality of included articles by the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2), the phases classification criteria for image mining studies, and the radiomics quality scoring (RQS) tool.

METHODS

We searched for eligible articles in the MEDLINE/PubMed and EMBASE databases using the terms "radiomics", "texture" and "lymphoma". The included studies were divided into two categories: diagnosis-, therapy response- and outcome-related studies. The diagnosis-related studies were evaluated using the QUADAS-2; all studies were evaluated using the phases classification criteria for image mining studies and the RQS tool by two reviewers.

RESULTS

Forty-five studies were included; thirteen papers (28.9%) focused on the differential diagnosis of primary central nervous system lymphoma (PCNSL) and glioblastoma (GBM). Thirty-two (71.1%) studies were classified as discovery science according to the phase classification criteria for image mining studies. The mean RQS score of all studies was 14.2% (ranging from 0.0 to 40.3%), and 23 studies (51.1%) were given a score of < 10%.

CONCLUSION

The radiomics features could serve as diagnostic and prognostic indicators in lymphoma. However, the current conclusions should be interpreted with caution due to the suboptimal quality of the studies. In order to introduce radiomics into lymphoma clinical settings, the lesion segmentation and selection, the influence of the pathological pattern and the extraction of multiple modalities and multiple time points features need to be further studied.

KEY POINTS

• The radiomics approach may provide useful information for diagnosis, prediction of the therapy response, and outcome of lymphoma. • The quality of published radiomics studies in lymphoma has been suboptimal to date. • More studies are needed to examine lesion selection and segmentation, the influence of pathological patterns, and the extraction of multiple modalities and multiple time point features.

Development and validation of an 18F-FDG PET radiomic model for prognosis prediction in patients with nasal-type extranodal natural killer/T cell lymphoma

OBJECTIVES

To identify an ¹⁸F-fluorodeoxyglucose (¹⁸F-FDG) positron emission tomography (PET) radiomics-based model for predicting progression-free survival (PFS) and overall survival (OS) of nasal-type extranodal natural killer/T cell lymphoma (ENKTL).

METHODS

In this retrospective study, a total of 110 ENKTL patients were divided into a training cohort (n = 82) and a validation cohort (n = 28). Forty-one features were extracted from pretreatment PET images of the patients. Least absolute shrinkage and selection operator (LASSO) regression was used to develop the radiomic signatures (R-signatures). A radiomics-based model was built and validated in the two cohorts and compared with a metabolism-based model.

RESULTS

The R-signatures were constructed with moderate predictive ability in the training and validation cohorts (R-signature_PFS: AUC = 0.788 and 0.473; R-signature_OS: AUC = 0.637 and 0.730). For PFS, the radiomics-based model showed better discrimination than the metabolism-based model in the training cohort (C-index = 0.811 vs. 0.751) but poorer discrimination in the validation cohort (C-index = 0.588 vs. 0.693). The calibration of the radiomics-based model was poorer than that of the metabolism-based model (training cohort: p = 0.415 vs. 0.428, validation cohort: p = 0.228 vs. 0.652). For OS, the performance of the radiomics-based model was poorer (training cohort: C-index = 0.818 vs. 0.828, p = 0.853 vs. 0.885; validation cohort: C-index = 0.628 vs. 0.753, p < 0.05 vs. 0.913).

CONCLUSIONS

Radiomic features derived from PET images can predict the outcomes of patients with ENKTL, but the performance of the radiomics-based model was inferior to that of the metabolism-based model.

KEY POINTS

• The R-signatures calculated by using ¹⁸F-FDG PET radiomic features can predict the survival of patients with ENKTL. • The radiomics-based models integrating the R-signatures and clinical factors achieved good predictive values. • The performance of the radiomics-based model was inferior to that of the metabolism-based model in the two cohorts.

CT-based Radiomic Signatures for Predicting Histopathologic Features in Head and Neck Squamous Cell Carcinoma

Purpose

To determine the performance of CT-based radiomic features for noninvasive prediction of histopathologic features of tumor grade, extracapsular spread, perineural invasion, lymphovascular invasion, and human papillomavirus status in head and neck squamous cell carcinoma (HNSCC).

Materials and Methods

In this retrospective study, which was approved by the local institutional ethics committee, CT images and clinical data from patients with pathologically proven HNSCC from The Cancer Genome Atlas (n = 113) and an institutional test cohort (n = 71) were analyzed. A machine learning model was trained with 2131 extracted radiomic features to predict tumor histopathologic characteristics. In the model, principal component analysis was used for dimensionality reduction, and regularized regression was used for classification.

Results

The trained radiomic model demonstrated moderate capability of predicting HNSCC features. In the training cohort and the test cohort, the model achieved a mean area under the receiver operating characteristic curve (AUC) of 0.75 (95% confidence interval [CI]: 0.68, 0.81) and 0.66 (95% CI: 0.45, 0.84), respectively, for tumor grade; a mean AUC of 0.64 (95% CI: 0.55, 0.62) and 0.70 (95% CI: 0.47, 0.89), respectively, for perineural invasion; a mean AUC of 0.69 (95% CI: 0.56, 0.81) and 0.65 (95% CI: 0.38, 0.87), respectively, for lymphovascular invasion; a mean AUC of 0.77 (95% CI: 0.65, 0.88) and 0.67 (95% CI: 0.15, 0.80), respectively, for extracapsular spread; and a mean AUC of 0.71 (95% CI: 0.29, 1.0) and 0.80 (95% CI: 0.65, 0.92), respectively, for human papillomavirus status.

Conclusion

Radiomic CT models have the potential to predict characteristics typically identified on pathologic assessment of HNSCC.Supplemental material is available for this article.© RSNA, 2020.

Radiogenomics Based on PET Imaging

Radiogenomics or imaging genomics is a novel omics strategy of associating imaging data with genetic information, which has the potential to advance personalized medicine. Imaging features extracted from PET or PET/CT enable assessment of in vivo functional and physiological activity and provide comprehensive tumor information non-invasively. However, PET features are considered secondary to features on conventional imaging, and there has not yet been a review of the radiogenomic approach using PET features. This review article summarizes the current state of PET-based radiogenomic research for cancer, which discusses some of its limitations and directions for future study.

Heterogeneity in tumours: Validating the use of radiomic features on 18F-FDG PET/CT scans of lung cancer patients as a prognostic tool

AIM

The aim was to validate promising radiomic features (RFs)1 on 18F-flourodeoxyglucose positron emission tomography/computed tomography-scans (18F-FDG PET/CT) of non-small cell lung cancer (NSCLC) patients undergoing definitive chemo-radiotherapy.

METHODS

18F-FDG PET/CT scans performed for radiotherapy (RT) planning were retrieved. Auto-segmentation with visual adaption was used to define the primary tumour on PET images. Six pre-selected prognostic and reproducible PET texture -and shape-features were calculated using texture respectively shape analysis. The correlation between these RFs and metabolic active tumour volume (MTV)3, gross tumour volume (GTV)4 and maximum and mean of standardized uptake value (SUV)5 was tested with a Spearman's Rank test. The prognostic value of RFs was tested in a univariate cox regression analysis and a multivariate cox regression analysis with GTV, clinical stage and histology. P-value ≤ 0.05 were considered significant.

RESULTS

Image analysis was performed for 233 patients: 145 males and 88 females, mean age of 65.7 and clinical stage II-IV. Mean GTV was 129.87 cm3 (SD 130.30 cm3). Texture and shape-features correlated more strongly to MTV and GTV compared to SUV-measurements. Four RFs predicted PFS in the univariate analysis. No RFs predicted PFS in the multivariate analysis, whereas GTV and clinical stage predicted PFS (p = 0.001 and p = 0.008 respectively).

CONCLUSION

The pre-selected RFs were insignificant in predicting PFS in combination with GTV, clinical stage and histology. These results might be due to variations in technical parameters. However, it is relevant to question whether RFs are stable enough to provide clinically useful information.

Robust, independent and relevant prognostic 18F-fluorodeoxyglucose positron emission tomography radiomics features in non-small cell lung cancer: Are there any?

In locally advanced lung cancer, established baseline clinical variables show limited prognostic accuracy and ¹⁸F-fluorodeoxyglucose positron emission tomography (FDG PET) radiomics features may increase accuracy for optimal treatment selection. Their robustness and added value relative to current clinical factors are unknown. Hence, we identify robust and independent PET radiomics features that may have complementary value in predicting survival endpoints. A 4D PET dataset (n = 70) was used for assessing the repeatability (Bland-Altman analysis) and independence of PET radiomics features (Spearman rank: |ρ|<0.5). Two 3D PET datasets combined (n = 252) were used for training and validation of an elastic net regularized generalized logistic regression model (GLM) based on a selection of clinical and robust independent PET radiomics features (GLM_all). The fitted model performance was externally validated (n = 40). The performance of GLM_all (measured with area under the receiver operating characteristic curve, AUC) was highest in predicting 2-year overall survival (0.66±0.07). No significant improvement was observed for GLM_all compared to a model containing only PET radiomics features or only clinical variables for any clinical endpoint. External validation of GLM_all led to AUC values no higher than 0.55 for any clinical endpoint. In this study, robust independent FDG PET radiomics features did not have complementary value in predicting survival endpoints in lung cancer patients. Improving risk stratification and clinical decision making based on clinical variables and PET radiomics features has still been proven difficult in locally advanced lung cancer patients.

Machine learning helps identifying volume-confounding effects in radiomics

PURPOSE

Highlighting the risk of biases in radiomics-based models will help improve their quality and increase usage as decision support systems in the clinic. In this study we use machine learning-based methods to identify the presence of volume-confounding effects in radiomics features. Methods 841 radiomics features were extracted from two retrospective publicly available datasets of lung and head neck cancers using open source software. Unsupervised hierarchical clustering and principal component analysis (PCA) identified relations between radiomics and clinical outcomes (overall survival). Bootstrapping techniques with logistic regression verified features' prognostic power and robustness. Results Over 80% of the features had large pairwise correlations. Nearly 30% of the features presented strong correlations with tumor volume. Using volume-independent features for clustering and PCA did not allow risk stratification of patients. Clinical predictors outperformed radiomics features in bootstrapping and logistic regression. Conclusions The adoption of safeguards in radiomics is imperative to improve the quality of radiomics studies. We proposed machine learning (ML) - based methods for robust radiomics signatures development.

Association of MRI-derived radiomic biomarker with disease-free survival in patients with early-stage cervical cancer

Pre-treatment survival prediction plays a key role in many diseases. We aimed to determine the prognostic value of pre-treatment Magnetic Resonance Imaging (MRI) based radiomic score for disease-free survival (DFS) in patients with early-stage (IB-IIA) cervical cancer.

Methods: A total of 248 patients with early-stage cervical cancer underwent radical hysterectomy were included from two institutions between January 1, 2011 and December 31, 2017, whose MR imaging data, clinicopathological data and DFS data were collected. Patients data were randomly divided into the training cohort (n = 166) and the validation cohort (n=82). Radiomic features were extracted from the pre-treatment T2-weighted (T2w) and contrast-enhanced T1-weighted (CET1w) MR imagings for each patient. Least absolute shrinkage and selection operator (LASSO) regression and Cox proportional hazard model were applied to construct radiomic score (Rad-score). According to the cutoff of Rad-score, patients were divided into low- and high- risk groups. Pearson's correlation and Kaplan-Meier analysis were used to evaluate the association of Rad-score with DFS. A combined model incorporating Rad-score, lymph node metastasis (LNM) and lymphovascular space invasion (LVI) by multivariate Cox proportional hazard model was constructed to estimate DFS individually.

Results: Higher Rad-scores were significantly associated with worse DFS in the training and validation cohorts (P<0.001 and P=0.011, respectively). The Rad-score demonstrated better prognostic performance in estimating DFS (C-index, 0.753; 95% CI: 0.696-0.805) than the clinicopathological features (C-index, 0.632; 95% CI: 0.567-0.700). However, the combined model showed no significant improvement (C-index, 0.714; 95%CI: 0.642-0.784).

Conclusion: The results demonstrated that MRI-derived Rad-score can be used as a prognostic biomarker for patients with early-stage (IB-IIA) cervical cancer, which can facilitate clinical decision-making.

Can Laws Be a Potential PET Image Texture Analysis Approach for Evaluation of Tumor Heterogeneity and Histopathological Characteristics in NSCLC?

We investigated the association between the textural features obtained from ¹⁸F-FDG images, metabolic parameters (SUVmax_, SUVmean, MTV, TLG), and tumor histopathological characteristics (stage and Ki-67 proliferation index) in non-small cell lung cancer (NSCLC). The FDG-PET images of 67 patients with NSCLC were evaluated. MATLAB technical computing language was employed in the extraction of 137 features by using first order statistics (FOS), gray-level co-occurrence matrix (GLCM), gray-level run length matrix (GLRLM), and Laws' texture filters. Textural features and metabolic parameters were statistically analyzed in terms of good discrimination power between tumor stages, and selected features/parameters were used in the automatic classification by k-nearest neighbors (k-NN) and support vector machines (SVM). We showed that one textural feature (gray-level nonuniformity, GLN) obtained using GLRLM approach and nine textural features using Laws' approach were successful in discriminating all tumor stages, unlike metabolic parameters. There were significant correlations between Ki-67 index and some of the textural features computed using Laws' method (r = 0.6, p = 0.013). In terms of automatic classification of tumor stage, the accuracy was approximately 84% with k-NN classifier (k = 3) and SVM, using selected five features. Texture analysis of FDG-PET images has a potential to be an objective tool to assess tumor histopathological characteristics. The textural features obtained using Laws' approach could be useful in the discrimination of tumor stage.

Does Measurement of First-Order and Heterogeneity Parameters Improve Response Assessment of Bone Metastases in Breast Cancer Compared to SUVmax in [18F]fluoride and [18F]FDG PET?

PURPOSE

To establish whether first-order statistical features from [18F]fluoride and 2-deoxy-2-[18F] fluoro-D-glucose ([18F]FDG) positron emission tomography/x-ray computed tomography (PET/CT) demonstrate incremental value in skeletal metastasis response assessment compared with maximum standardised uptake value (SUVmax).

PROCEDURES

Sixteen patients starting endocrine treatment for de novo or progressive breast cancer bone metastases were prospectively recruited to undergo [18F]fluoride and [18F]FDG PET/CT scans before and 8 weeks after treatment. Percentage changes in SUV parameters, metabolic tumour volume (MTV), total lesion metabolism (TLM), standard deviation (SD), entropy, uniformity and absolute changes in kurtosis and skewness, from the same ≤ 5 index lesions, were measured. Clinical response to 24 weeks, assessed by two experienced oncologists blinded to PET/CT imaging findings, was used as a reference standard and associations were made between parameters and progression free and overall survival.

RESULTS

[18F]fluoride PET/CT: In four patients (20 lesions) with progressive disease (PD), TLM and kurtosis predicted PD better than SUVmax on a patient basis (4, 4 and 3 out of 4, respectively) and TLM, entropy, uniformity and skewness on a lesion basis (18, 16, 16, 18 and 15 out of 20, respectively). Kurtosis was independently associated with PFS (p = 0.033) and OS (p = 0.008) on Kaplan-Meier analysis. [18F]FDG PET: No parameter provided incremental value over SUVmax in predicting PD or non-PD. TLM was significantly associated with OS (p = 0.041) and skewness with PFS (p = 0.005). Interlesional heterogeneity of response was seen in 11/16 and 8/16 patients on [18F]fluoride and [18F]FDG PET/CT, respectively.

CONCLUSION

With [18F]fluoride PET/CT, some first-order features, including those that take into account lesion volume but also some heterogeneity parameters, provide incremental value over SUVmax in predicting clinical response and survival in breast cancer patients with bone metastases treated with endocrine therapy. With [18F]FDG PET/CT, no first-order parameters were more accurate than SUVmax although TLM and skewness were associated with OS and PFS, respectively. Intra-patient heterogeneity of response occurs commonly between metastases with both tracers and most parameters.